Genome Understanding Evaluation (GUE)
28 datasets/tasks in the native packaging; mapped here to five task families.
1 benchmark-wide protocols · 10 benchmark-wide rows (not a task subtotal)D1 · Sequence understanding & regulation
Genomic element classification
Classify sequence windows as promoters, enhancers, exons, introns or other genomic elements.
Task definition
- Input granularity
- sequence/window
- Biological target
- coding and non-coding element identity
- Output representation
- class label
- ML formulation
- classification
- Counting notes
- NR
Benchmark coverage
6 benchmarks cover this task
Nucleotide Transformer benchmark
Eighteen downstream tasks are benchmark instances, not eighteen unique task families.
67 benchmark-wide protocols · 821 benchmark-wide rows (not a task subtotal)GenBench
Framework and dataset suite; native task count follows current release documentation.
0 benchmark-wide protocols · 0 benchmark-wide rows (not a task subtotal)Genomic Benchmarks
Widely reused classification datasets; simple random-style splits can inflate biological generalization.
0 benchmark-wide protocols · 0 benchmark-wide rows (not a task subtotal)Benchmarking DNA foundation models for genomic and genetic tasks
One-time benchmark study rather than a maintained benchmark suite.
6 benchmark-wide protocols · 8 benchmark-wide rows (not a task subtotal)OmniGenBench
Meta-suite packaging RGB, BEACON, GUE, Genomic Benchmarks and PGB; native_task_count=5 suites, not the sum of their downstream tasks.
0 benchmark-wide protocols · 0 benchmark-wide rows (not a task subtotal)Evaluation protocols
8 protocol units
| Protocol | Track | Split / subset | Comparability |
|---|---|---|---|
PROT-B01-28-DATASET-AGGREGATE-OFFICIAL-TRAIN-0DD5CD98-5E300CAE | 28-dataset aggregate B01-TR01 | official train/validation/test splits 28 GUE datasets across seven task categories | same_table_comparable inference_budget |
PROT-B03-GENE-FINDING-OFFICIAL-4780-597-597--6344D314-B008E220 | gene_finding NR | official 4780/597/597 split gene finding | same_table_comparable inference_budget |
PROT-B02-18-TASK-AGGREGATE-TENFOLD-CROSS-VAL-FCCB80F7-23197296 | 18-task aggregate B02-TR01 | tenfold cross-validation test folds 18 curated downstream tasks | same_table_comparable external_data_policy;inference_budget |
PROT-B10-CODING-POTENTIAL-ACCURACY-HUMAN-ACC-741380E6-0AE2B9A5 | Coding Potential NR | Accuracy (human) Accuracy (human) | official_board_comparable external_data_policy;inference_budget |
PROT-B10-CODING-POTENTIAL-ACCURACY-MOUSE-ACC-3932E6F5-00414C51 | Coding Potential NR | Accuracy (mouse) Accuracy (mouse) | official_board_comparable external_data_policy;inference_budget |
PROT-B10-CODING-POTENTIAL-ACCURACY-ZEBRAFISH-282FE984-7798F892 | Coding Potential NR | Accuracy (zebrafish) Accuracy (zebrafish) | official_board_comparable external_data_policy;inference_budget |
PROT-B10-CODING-POTENTIAL-ACCURACY-FRUIT-FLY-2D793F06-91EDA136 | Coding Potential NR | Accuracy (fruit_fly) Accuracy (fruit_fly) | official_board_comparable external_data_policy;inference_budget |
PROT-B10-CODING-POTENTIAL-ACCURACY-S-CEREVIS-7B4DEC54-6B0EC743 | Coding Potential NR | Accuracy (s_cerevisia) Accuracy (s_cerevisia) | official_board_comparable external_data_policy;inference_budget |